© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9188
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on LaTeX‐style mathematical notation—especially set, interval, and formula delimiters (braces, parentheses, backslashes, “\mathbb,” etc.) in math expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -2.31
    entown
    -1.57
    isait
    -1.57
     Wirkungen
    -1.43
     circonstances
    -1.41
    裒
    -1.39
    then
    -1.37
    燜
    -1.31
    unno
    -1.30
    titial
    -1.30
    POSITIVE LOGITS
    姈
    1.53
     permitan
    1.34
     competitivos
    1.23
     segü
    1.20
    beitung
    1.19
     zowel
    1.19
     duide
    1.18
     referirse
    1.17
    bois
    1.16
     lavado
    1.16
    Activations Density 0.042%

    No Known Activations